得州大学论文提出 Jev-Mem：长对话记忆构建提速 6.6 倍
University of Texas paper finds that handing small memory decisions to a fast scoring model let an AI memory system build its memory of long conversations 6.6 t
得克萨斯大学论文提出的 Jev-Mem 把链接、停止搜索等小型记忆决策交给快速打分模型 Jev，以批量返回概率替代生成文本，只在最后调用 LLM 读取记忆并作答，使长对话记忆构建速度提升 6.6 倍。在 LoCoMo 长对话基准上，其回答得分为 0.777，高于最佳基线的 0.700；记忆构建耗时 158 秒，最快对比方案为 1,044 秒，回答耗时 0.93 秒，对比方案为 1.47 秒。作者建议，若记忆流水线在路由、打分或停止判断上调用 LLM，可改用快速分类器，把 LLM 留给最终回答。
正文
University of Texas paper finds that handing small memory decisions to a fast scoring model let an AI memory system build its memory of long conversations 6.6 times faster
Many memory systems ask an LLM to make small choices, like what to link or when to stop searching.
Generating text for each choice is slow, and those calls pile up during memory building and search.
Jev-Mem gives those choices to a fast scorer, Jev, that returns probabilities in batches instead of text. The LLM is called only at the end, to read the chosen memories and answer.
On the LoCoMo long-conversation benchmark, it got a 0.777 answer score versus 0.700 for the best baseline. It built memory in 158 seconds versus 1,044 for the fastest rival and answered in 0.93 seconds versus 1.47.
If your memory pipeline calls an LLM for routing, scoring, or stopping, try a fast classifier there and save the LLM for answers.